{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:UMFKTNZTLFWUREPRT6TQXWSOZT","short_pith_number":"pith:UMFKTNZT","schema_version":"1.0","canonical_sha256":"a30aa9b733596d4891f19fa70bda4ecce5224aa17e49642a73193ec5af8092b3","source":{"kind":"arxiv","id":"2603.11042","version":2},"attestation_state":"computed","paper":{"title":"V2M-Zero: Zero-Pair Time-Aligned Video-to-Music Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Event curves from intra-modal similarities enable zero-pair training for time-aligned video-to-music generation.","cross_cats":["cs.AI","cs.LG","cs.MM","cs.SD"],"primary_cat":"cs.CV","authors_text":"Aniruddha Mahapatra, Gedas Bertasius, Jonah Casebeer, Long Mai, Nicholas J. Bryan, Yan-Bo Lin","submitted_at":"2026-03-11T17:59:40Z","abstract_excerpt":"Generating music that temporally aligns with video events is challenging for existing text-to-music models, which lack fine-grained temporal control. We introduce V2M-ZERO, a video-to-music generation approach that generates time-aligned music with disentangled time synchronization and semantic control (e.g., genre, mood) from video while requiring zero video-music pairs at training time. Our method is motivated by a key observation: temporal synchronization requires matching when and how much change occurs, not what changes. While musical and visual events differ semantically, they exhibit sh"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":true,"formal_links_present":false},"canonical_record":{"source":{"id":"2603.11042","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-03-11T17:59:40Z","cross_cats_sorted":["cs.AI","cs.LG","cs.MM","cs.SD"],"title_canon_sha256":"9ce94ec5dd521de0c93a5a80de2650e063ef221485df1654582f86cefdee8b29","abstract_canon_sha256":"2b4b7795a47e7fa658aaba5829c96d404691d5ce7cce175803fa0ef7b792c5ee"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:15.822193Z","signature_b64":"R/96yWsYnAIAqGCHlWWZmA9SyX3fbAlCW4n0JrqPff5TwtUeNPogVzxovCMeYHxDr6RF+9nCY4GlLCTe0OeJDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a30aa9b733596d4891f19fa70bda4ecce5224aa17e49642a73193ec5af8092b3","last_reissued_at":"2026-05-17T23:39:15.821418Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:15.821418Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"V2M-Zero: Zero-Pair Time-Aligned Video-to-Music Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Event curves from intra-modal similarities enable zero-pair training for time-aligned video-to-music generation.","cross_cats":["cs.AI","cs.LG","cs.MM","cs.SD"],"primary_cat":"cs.CV","authors_text":"Aniruddha Mahapatra, Gedas Bertasius, Jonah Casebeer, Long Mai, Nicholas J. Bryan, Yan-Bo Lin","submitted_at":"2026-03-11T17:59:40Z","abstract_excerpt":"Generating music that temporally aligns with video events is challenging for existing text-to-music models, which lack fine-grained temporal control. We introduce V2M-ZERO, a video-to-music generation approach that generates time-aligned music with disentangled time synchronization and semantic control (e.g., genre, mood) from video while requiring zero video-music pairs at training time. Our method is motivated by a key observation: temporal synchronization requires matching when and how much change occurs, not what changes. While musical and visual events differ semantically, they exhibit sh"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Our results validate that temporal alignment through within-modality features is not only effective for video-to-music generation but also leads to better performance than paired cross-modal supervision.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The assumption that event curves computed from intra-modal similarity using pretrained encoders provide comparable representations across modalities that enable direct substitution at inference without cross-modal training.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"V2M-Zero achieves state-of-the-art video-to-music generation with improved temporal synchronization and semantic alignment by substituting video event curves into a fine-tuned text-to-music model without any paired training data.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Event curves from intra-modal similarities enable zero-pair training for time-aligned video-to-music generation.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"631dd9d8567114de0a7cf6dfb1396539d5e207347054698406d1cccea66d4aad"},"source":{"id":"2603.11042","kind":"arxiv","version":2},"verdict":{"id":"a84a8d18-b87e-4bbe-8251-34e5a67ac0a1","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T13:15:18.525988Z","strongest_claim":"Our results validate that temporal alignment through within-modality features is not only effective for video-to-music generation but also leads to better performance than paired cross-modal supervision.","one_line_summary":"V2M-Zero achieves state-of-the-art video-to-music generation with improved temporal synchronization and semantic alignment by substituting video event curves into a fine-tuned text-to-music model without any paired training data.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The assumption that event curves computed from intra-modal similarity using pretrained encoders provide comparable representations across modalities that enable direct substitution at inference without cross-modal training.","pith_extraction_headline":"Event curves from intra-modal similarities enable zero-pair training for time-aligned video-to-music generation."},"references":{"count":111,"sample":[{"doi":"","year":2023,"title":"MusicLM: Generating music from text.arXiv Preprint, 2023","work_id":"2215fdec-d5ee-48e4-9cb0-ca5e6104f20b","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"V-JEPA 2: Self-supervised video models enable understanding, prediction and planning.arXiv Preprint, 2025","work_id":"9319b4a4-f8e2-4c38-a4ca-731350281b54","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Yatong Bai, Jonah Casebeer, Somayeh Sojoudi, and Nicholas J. Bryan. DRAGON: Distributional rewards optimize diffusion generative models.TMLR,","work_id":"68f8c904-2857-4323-8f15-d5591a0652a2","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"AudioLM: a language modeling approach to audio generation","work_id":"b3eb82aa-6361-4788-98e1-566428a7f6aa","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Re-bottleneck: Latent re-structuring for neural audio autoencoders","work_id":"3ad4f3bd-241d-4346-b0a6-56a238439438","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":111,"snapshot_sha256":"3625d217df5d9c16ea8df15d8d698ffbe34cbf6447666061623d45de0a656f6b","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2603.11042","created_at":"2026-05-17T23:39:15.821559+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.11042v2","created_at":"2026-05-17T23:39:15.821559+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.11042","created_at":"2026-05-17T23:39:15.821559+00:00"},{"alias_kind":"pith_short_12","alias_value":"UMFKTNZTLFWU","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"UMFKTNZTLFWUREPR","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"UMFKTNZT","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UMFKTNZTLFWUREPRT6TQXWSOZT","json":"https://pith.science/pith/UMFKTNZTLFWUREPRT6TQXWSOZT.json","graph_json":"https://pith.science/api/pith-number/UMFKTNZTLFWUREPRT6TQXWSOZT/graph.json","events_json":"https://pith.science/api/pith-number/UMFKTNZTLFWUREPRT6TQXWSOZT/events.json","paper":"https://pith.science/paper/UMFKTNZT"},"agent_actions":{"view_html":"https://pith.science/pith/UMFKTNZTLFWUREPRT6TQXWSOZT","download_json":"https://pith.science/pith/UMFKTNZTLFWUREPRT6TQXWSOZT.json","view_paper":"https://pith.science/paper/UMFKTNZT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.11042&json=true","fetch_graph":"https://pith.science/api/pith-number/UMFKTNZTLFWUREPRT6TQXWSOZT/graph.json","fetch_events":"https://pith.science/api/pith-number/UMFKTNZTLFWUREPRT6TQXWSOZT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UMFKTNZTLFWUREPRT6TQXWSOZT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UMFKTNZTLFWUREPRT6TQXWSOZT/action/storage_attestation","attest_author":"https://pith.science/pith/UMFKTNZTLFWUREPRT6TQXWSOZT/action/author_attestation","sign_citation":"https://pith.science/pith/UMFKTNZTLFWUREPRT6TQXWSOZT/action/citation_signature","submit_replication":"https://pith.science/pith/UMFKTNZTLFWUREPRT6TQXWSOZT/action/replication_record"}},"created_at":"2026-05-17T23:39:15.821559+00:00","updated_at":"2026-05-17T23:39:15.821559+00:00"}